How real projects summarise themselves for language models.
ChaoYue0307llms.txtChaoYue0307/awesome-loop-engineering/docs/llms.txt
maturity model - [Working definition](https://github.com/ChaoYue0307/awesome-loop-engineering/blob/main/DEFINITION.md): short definition, positioning, and minimal loop test - [Taxonomy](https://github.com/ChaoYue0307/awesome-loop-engineering/blob/main/TAXONOMY.md): classification by trigger, intake, verification, state model, and topology - [Anti-patterns
hqhq1025llms.txthqhq1025/clipaste/docs/llms-full.txt
support depends on the compositor and source application; universal desktop compatibility has not been tested. | OS / context | Local clipboard-host daemon | Consumer of another host's clipboard | |---|---|---| | macOS | Supported
hqhq1025llms.txthqhq1025/clipaste/docs/llms.txt
popup workaround is used. - GNOME Wayland may need the XWayland clipboard bridge. Reporters must test a screenshot copied from a native Wayland app, re-run `doctor`, and verify the image
open-agreementsllms.txtopen-agreements/open-agreements/llms-full.txt
compete statute, so every post-employment restraint stands or falls on Arizona's reasonableness test — a restriction is unreasonable and will not be enforced if it is greater than necessary
clawboollms.txtclawboo/clawboo/docs/llms.txt
ScheduleSource — that mirror AgentSource and merge per-source adapters into one normalized record stream. - [Testing strategy](internals/testing.md): How Clawboo verifies itself — the two Vitest projects, sandboxed Playwright e2e, the clean
johnxiellms.txtjohnxie/awesome-code-docs/llms-full.txt
from HKUDS that lets you describe agents in plain English and have them generated, tested, and deployed automatically. With 9,116 GitHub stars and an academic paper (arxiv
PavanMudigondallms.txtPavanMudigonda/zero-to-ai/llms-full.txt
Face Spaces, Flowise, Langflow, Dify, AutoML platforms. ### Phase 19 - AI Safety & Red Teaming Adversarial testing, content moderation, PII protection, bias mitigation, jailbreak prevention. ### Phase 20 - Real-Time Streaming Token
PavanMudigondallms.txtPavanMudigonda/zero-to-ai/llms.txt
Time Series Analysis - ARIMA, Prophet, Transformer Forecasting - Phase 27: Causal Inference - DAGs, A/B Testing, Observational Methods - Phase 28: Practical Data Science - Interview Prep, End-to-End Projects - Phase
ThreatRecallllms.txtThreatRecall/zettelforge/docs/llms.txt
Python Standards: ruff lint, ruff format, mypy `disallow_untyped_defs` (build/CI gate) - **GOV-007** — Testing Standards: pytest with `--cov-fail-under=67` (build/CI gate) - **GOV-011** — Access Control & Input Validation
oldskultxollms.txtoldskultxo/aictx/docs/llms-full.txt
sessions. - Decision memory: explicit decisions future agents should not rediscover. - Failure memory: observed command, test, build, lint, and typecheck failures plus resolution links. - Strategy memory: successful observed approaches that
dcc-mcpllms.txtdcc-mcp/dcc-mcp-maya/llms-full.txt
enable defensive `__del__` guard. Off in interactive Maya (Tokio deadlock risk); recommended for `mayapy` / test fixtures (issue #186). | | `DCC_MCP_MAYA_RESOURCES` | `1` | per-process | `0`=disable Maya MCP resource
dcc-mcpllms.txtdcc-mcp/dcc-mcp-maya/llms.txt
host dispatcher); `dcc` flips `True` synchronously in inline-executor mode (no host dispatcher — `mayapy` / tests) or after the first main-thread pump when a real host dispatcher is attached
dearlordylordllms.txtdearlordylord/huly-mcp/site/llms.txt
recruiting, SDK discovery, security administration, sequence administration, spaces, support, tag categories, tags, task management, test management, user statuses, views, virtual office, Workbench, and workflow statuses. ## Agent Notes - Prefer user-level
OptimNowllms.txtOptimNow/cloud-finops-skills/llms-full.txt
Traditional software with GenAI bolted into one or more steps | Bounded per invocation | Standard test set | | **Pipeline** | Predetermined steps, LLM called at one or more of them (most chatbots) | Bounded
monteslullms.txtmonteslu/vibe-eyes/llms.txt
bugs 2. **Visual feedback** - Describe what's on screen to the LLM 3. **Automated testing** - Verify visual output programmatically 4. **Accessibility** - Convert visual content to descriptions ## Related Projects - [vibe-eyes
sfrangulovllms.txtsfrangulov/claude-code-handbook-ru/llms-full.txt
# Claude Code Handbook на русском — full text > Все материалы handbook одним файлом для подгрузки
karthikrshetllms.txtkarthikrshet/Career-Agents/llms-full.txt
sending the resume. - **Resume A/B experiment design:** Build a minimal tracker and simple hypothesis tests to compare two resume variants' response rates over a statistically meaningful window. - **Role-profile engineering
karthikrshetllms.txtkarthikrshet/Career-Agents/llms.txt
founder-advisor | Path: startup/founder-advisor.md) Description: A blunt, experienced-feeling co-founder substitute who stress-tests ideas and decisions the way a real early-stage advisor would — before money, time
Rtur2003llms.txtRtur2003/Claude-Code-Promts-Skills/llms.txt
code (specialist prompts) - Code review: ./prompts/english/agents/code-review-prompt.md - Security audit: ./prompts/english/agents/security-audit-prompt.md - Debugging / incident: ./prompts/english/agents/debugging-troubleshooting-prompt.md - Refactoring: ./prompts/english/agents/refactoring-prompt.md - Testing strategy: ./prompts/english/agents/testing-strategies-prompt.md - Performance: ./prompts/english/agents/performance-optimization-prompt.md - Migration / upgrade: ./prompts/english/agents/migration-upgrade-prompt.md - Monitoring / observability: ./prompts/english/agents/monitoring-observability-prompt.md - Error handling / resilience: ./prompts/english/agents/error-handling-resilience-prompt.md - Accessibility
Kanevryllms.txtKanevry/session-orchestrator/site/llms-full.txt
Core, Impl-Polish, Quality, Finalization) with quality checks between waves and a full configured test, typecheck and lint gate before completion. Claude Code and Codex can dispatch parallel agents; Cursor
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
